Sage Journals: Discover world-class research

Abstract

Background:

Tendinopathies of the long head of the biceps (LHB) are a common issue in shoulder surgery.

Purpose/Hypothesis:

The purpose of this study is to determine whether the red discoloration observed in the LHB and synovial rotator cuff interval during arthroscopy invariably indicates significant inflammation, which is frequently used to guide therapeutic decisions about LHB tenotomy or tenodesis. Red coloration of the LHB and the surrounding rotator cuff interval would not necessarily be related to the clinical symptoms of the patient.

Study Design:

Cross-sectional study; Level of evidence, 3.

Methods:

Patients undergoing arthroscopy for symptomatic LHB pathology were included in the study if they met the inclusion criteria. Images of patients who were undergoing arthroscopy for other shoulder pathologies, but who did not exhibit LHB symptoms, were designated as the control group. Standardized imaging and video techniques were employed to identify the LHB and to calculate an objective measure of the total red component of the respective LHB. Machine learning (ML) was utilized to enumerate the respective red component in pixel count for each LHB, along with the redness of the synovial rotator cuff interval. The extent of effusion within the bicipital groove (as evident from axial slides of preoperative magnetic resonance imaging) was noted and subsequently correlated. The ranges into which the red hue of the LHB and the surrounding rotator cuff interval were divided included >60%, 60% to 31%, 30% to 11%, and <10%.

Results:

A total of 124 patients (men = 84, women = 40) were included, with a collective sum of 36,941 arthroscopy images (both standalone images and video frames). A total of 31 superior labral lesions, from anterior to posterior lesions, and 10 pulley lesions were detected. Moreover, 46 lesions were subjectively assessed by the surgeon as having LHB tendinitis based on LHB red “inflammation” staining intraoperatively. ML-based quantification revealed >60% LHB redness in 17 instances, between 60% to 31% in 22, between 30% to 11% in 33, and <10% in 52 instances. However, it could not be established that a significant statistical correlation exists between the intensity and extent of LHB redness, or the associated redness in the rotator interval, and their corresponding clinical symptoms related to LHB pathologies. In addition, there was no positive correlation between the effusion area and the LHB red staining, the surrounding sulcus bicipitalis area, or indications of pain.

Conclusion:

No positive correlation was found between the redness/intensity of the LHB on arthroscopy and the clinical symptoms within the LHB tests. The assessment of visually detectable “inflammation” of the LHB within arthroscopy as a therapeutic criterion must be questioned.

Keywords

arthroscopy long head of the biceps rotator cuff interval tendinitis

Tendon pathologies of the long head of the biceps (LHB) are common in shoulder surgery, spanning from acute tendinitis to degenerative conditions. The inflamed LHB often presents with accompanying pathologies, such as superior labral lesions from anterior to posterior (SLAP) or pulley lesions. For patients, LHB tendinopathies can result in protracted clinical profiles with significant limitations in daily life. The initial treatment approach is normally nonoperative, involving physical therapy or ultrasound-guided infiltrations. If these nonoperative therapies do not yield satisfactory results, it inevitably leads to arthroscopy, which addresses the LHB.^2,13,16

Operatively, pathologies of the LHB are typically treated using arthroscopy. The choice between tenodesis and tenotomy is influenced by the patient's needs, aesthetic expectations, and age.^7,8,11,13,20 Arthroscopy often reveals synovitis of both the rotator interval and the LHB. Increased vascular vessels and red coloration, which are generally associated with “inflammation,” are discerned and are identified as the cause of clinical symptoms, especially in cases devoid of substantial structural lesions (eg, SLAP or Pulley lesions). For instance, the term “lipstick LHB” is frequently employed in the literature to describe a scenario with complete red staining (“inflammation”) visible during arthroscopic examination. This is commonly accepted as a criterion for therapeutic decision-making, leading to tenotomy or tenodesis.^{1,5,8,20,24,29} Concomitant synovial inflammation in the glenohumeral joint can also cause anterior shoulder pain and is included in the study as an examination of the rotator cuff interval.

Preoperative magnetic resonance imaging (MRI) often interprets effusion in the LHB sulcus and signals elevations of the LHB in terms of tendinopathy.^{2,12,14,19,25} This study aimed to determine whether the clinical manifestation of LHB pain, positive clinical test results from the patient, and redness of the LHB and surrounding areas are indeed associated with increased detectable effusion in the bicipital sulcus through MRI imaging.

Using machine learning (ML)-based image segmentation techniques, the red staining of the LHB and the neighboring rotator cuff interval was quantified and correlated to the findings with the patient's clinical symptoms. The hypothesis posited that any clinical abnormalities experienced by the patient in relation to the LHB held no correlation to the red coloration detected intraoperatively within the LHB and the surrounding rotator interval. Therefore, the primary objective was to determine whether there is a correlation between visible red staining of the LHB and the surrounding rotator cuff interval and preoperative clinical signs of inflammation.

The secondary objective was to assess whether redness of the LHB correlates with increased detectable effusion in the bicipital sulcus on MRI.^12,28

Methods

Ethical approval for this study was obtained from the Ethical Board of Ruhr Universität Bochum (registration number: 16-5859). This was a retrospective cohort analysis. Patients were divided into study and control groups based on preoperative clinic assessments and MRI results.

The inclusion criteria for the study group were defined as follows: Isolated clinical symptoms of the LHB lasting at least 4 months with positive clinical LHB tests, and failure of nonoperative therapy, subsequently indicating the need for surgery. No age limit was set.

The exclusion criteria included concomitant rotator cuff lesions (identified in preoperative MRI or via arthroscopy), fractures, instabilities, or advanced degenerative changes (eg, osteoarthritis). Patients who had undergone arthroscopy for other pathologies—eg, for repair or acromioclavicular (AC) joint dislocation, Bankart lesion, but all with an intact rotator cuff—and presented no clinical symptoms of the LHB during clinical examination, were treated as a control group. No age limit was set. None of the patients had undergone an operation before.

All patients underwent preoperative examinations as part of a standard shoulder assessment performed by the same experienced shoulder surgeon. Special attention was given to the tests of the LHB, including pressure pain at the bicipital groove—visual analog scale, Yergason test, Palm-up test, and O’Brien test. In the Yergason test, the LHB is tensed by supination against resistance with the elbow flexed at a right angle. Provocation pain in the course of the bicipital sulcus can be intensified by palpation. In the palm-up test, the seated patient tries to hold his arm against the slight resistance with 90° abduction and 30° horizontal flexion and with the forearm supinated. In the O’Brien test, the standing patient moves his arm with the elbow extended into 90° flexion, adducts another 10° to 15° beyond the sagittal plane, and rotates maximally inwards. The examiner stands behind the patient and tries to push the patient’s arm downwards against resistance. The same test is performed in external rotation. The test is positive if pain is triggered during the first part, which then decreases with supination.^6,26 Depending on the literature surveyed, the specificity and sensitivity of the individual tests are low to moderate. For example, studies indicate a sensitivity of 57% and a specificity of 74% for the pressure point of the LHB. For the Yergason test, a sensitivity of between 14% and 75% and a specificity of between 78% and 89% are reported. The O’Brien test has a sensitivity of between 38% and 68% and a specificity of between 46% and 61%. The Palm-up or the Speed test has a sensitivity between 49% and 71% and a specificity of between⁹ 60% and 85%. However, all patients received a standardized clinical examination from an orthopaedic and trauma surgery specialist (M.A.B., M.K.). This examination specifically looked for existing impingement (The Neer-Hawkins tests) or AC joint pathologies (body cross sign). The presence of subacromial impingement or AC joint pathologies did not exclude patients from the study. In some circumstances within the study group, patients underwent infiltrations with Xylonest 1% and TriamHexal (Cortisone) 20 mg under sonography at the LHB once to exhaust nonoperative therapy (Table 1) in the month before surgery.

Table 1

Demographic and Clinical Parameters of the 2 Groups ^a

	Control Group	Examination Group
Group size, n	36 (M = 33, F = 3)	88 (M = 51, F = 37)
Mean age, years	32	49
No. of previous surgeries on the shoulder joint, not LHB	1	29
Infiltration (Xylonest 1%, TriamHexal 20 mg) in the month before surgery	0	22
Tenotomy	0	40
Tenodesis	0	31
Pressure point at LHB	0	82
VAS, mean value	0	6,4
Yergason test	0	44
Palm-up test	0	79
O‘Brien test	0	42

F, female; LHB, long head of the biceps; M, male; VAS, visual analog scale.

Both video and photographic material from all arthroscopies were included, featuring the LHB for delineation, and were analyzed retrospectively. Each video was divided into frames and assigned to a specific patient. Arthroscopy was conducted using standard portals by an experienced arthroscopist. To achieve a uniform image representation with the arthroscope positioned in the posterior portal, the LHB tendon was drawn into the shoulder joint using a palpation hook (introduced through the anterior standard portal). This allowed for recording the entire intra-articular biceps tendon course and the upper portion of the surrounding sulcus.

A diagnostic tour was conducted after establishing the standard portals for arthroscopy. During this, the insertion of the LHB at the upper glenoid rim, the pulley complex, the rotator cuff, and the course of the LHB were examined using tactile hook control. After the standard tour, an LHB tenotomy or LHB tenodesis was performed, based on the preoperative information provided. The latter procedure was conducted using a small subpectoral incision, a method following the Post procedures.

ML Segmentation

The analysis is based on the MASKRCNN_RESNET50_FPN architecture,^3,27 which is a deep learning model used for instance segmentation tasks. This model operates on the principle of supervised learning, which is less prone to errors due to its control mechanisms. It mixes 2 widely-used architectures—ResNet50 and Feature Pyramid Network (FPN)—adding a mask prediction branch. In summary, the MASKRCNN_RESNET50_FPN is a robust model architecture that has demonstrated remarkable performance across a wide variety of instance segmentation tasks in computer vision applications.^27,30

All images and video frames were included in the evaluation, whereby an orthopaedic and trauma surgery specialist determined whether the LHB was distinctly displayed (M.K.). All images explicitly featuring the LHB were subsequently used for training and testing an ML program. To objectively quantify the red coloration of the LHB and the surrounding rotator cuff interval, principles from computer science and ML were employed. Image segmentation, a component of ML, is crucial in computer vision as it partitions an image into multiple nonoverlapping regions, each relating to a specific object or background.

Using 200 images, the ML system, operating as supervised learning, was initially trained to recognize the LHB tendon and the rotator cuff interval. Upon the completion of image assessments, another random 400 images (displaying the LHB or otherwise) were selected for precision determination of the program.

The present visual representations are grouped into 4 distinct classes (Figures 1 -4), based on the LHB's spatial orientation. This pivotal factor was considered during the algorithm's training phase, and the corresponding positions have been labeled as “tendon in the foreground with dark background,”“tendon in the foreground with light background,”“tendon in the foreground with monochrome background,”“embedded tendon with monochrome background,” and “tendon with perspective and similar structures” (Figures 1 -4). The fifth image is an instance of a so-called “lipstick LHB” (Figure 5).

Figure 1.

Cut of the LHB tendon in the foreground with a dark background. LHB, long head of the biceps.

Figure 2.

Cut of the LHB tendon in the foreground with a light background. LHB, long head of the biceps.

Figure 3.

Cut of the LHB tendon in the foreground with a monochrome background. LHB, long head of the biceps.

Figure 4.

The embedded LHB Tendon with a monochrome background. LHB, long head of the biceps.

Figure 5.

Tendon with perspective and similar structures, an example of a so-called “lipstick LHB.” LHB, long head of the biceps.

In the first step, the images were segmented using ML, meaning the image sections were assigned to the corresponding identifiers: LHB and the surrounding area. Various, significantly contrasting colors were utilized for this. In the second step, the individual segments were reduced to red pixels using varying color scales (light/dark, red pigmentation). In all images and video frames where detectable LHB was present, the intensity of the red coloration in the surrounding rotator cuff interval was also examined. After confirming high precision, the algorithm was applied to all images and video frames. The ranges into which the red hue of the LHB and the surrounding rotator cuff interval were divided included >60%, 60% to 31%, 30% to 11%, and <10%.

Preoperative MRI

An effusion in the bicipital groove is depicted as an image morphologic correlate for tendon inflammation.¹² To quantify the effusion area, axial T2 images from all patients were examined (Figure 6). The sequence with the largest amount of fluid around the LHB was then measured (in mm²). In the same image, the LHB was also measured (in mm²) to calculate the absolute effusion area via subtraction.

Figure 6.

An example of the measurement of the effusion area in an axial T2 MRI image. MRI, magnetic resonance imaging.

Statistical Analysis

The demographic and clinical data were collected in Excel (Microsoft). The statistics were generated using Python 3.8 (Python Software Foundation, Python Language Reference, Version 2.8) and Jupyter 1.0.0 (Kluyver et al, 2016. Jupyter Notebooks). The calculations and visualizations utilized packages such as Pandas 1.2.0, NumPy 1.19.4, Seaborn 0.11.1, and SciPy 1.5.4. As a statistical method, the chi-square test (Pearson or Fisher, depending on the sample size) was applied throughout to test the stochastic independence in the contingency tables. The P value was always reported if the null hypothesis was significantly rejected at an alpha of .05. Upon evaluating the image files and categorizing the different shades of red, the data from the demographic and clinical evaluations were statistically correlated, and the significance levels were determined.

Results

Clinical Parameters

A total of 124 patients (84 men, 40 women) were included, with a total of 36,941 arthroscopy images (still images and video frames). There were 88 participants in the study group and 36 in the control group (Table 1).

In total, 173,023 arthroscopy images were incorporated, comprising both static images and video frames. The LHB was identified in over 15,000 cases by a specialist in orthopaedics and trauma surgery. A total of 200 labeled sample images were fed into the ML program. Despite the small size of the training set, which comprised only 200 images, the algorithm produced impressive results with an accuracy of 0.88. This precision was verified through a randomly selected sample of 400 automatically segmented images, both with and without the LHB.

Moreover, >60% redness of the LHB was observed in 17 patients (F = 3, M = 14, Group (Gr) LHB = 61%-100%), between 60% and 31% in 23 patients (F = 9, M = 14, Gr LHB = 31%-60%), between 30% and 11% in 33 patients (F = 11, M = 22, Gr LHB = 11%-30%), and <10% in 39 patients (F = 12, M = 27, Gr LHB = 0%-10%). In the surrounding rotator cuff interval excluding LHB, >60% redness was observed in 29 patients (F = 8, M = 21, Gr noLHB = 61%-100%), between 60% and 31% in 31 patients (F = 11, M = 20, Gr noLHB = 31%-60%), between 30% and 11% in 31 patients (F = 11, M = 20, Gr noLHB = 11%-30%), and <10% in 29 patients (F = 8, M = 21, Gr noLHB = 0%-10%). The percentage of red coloration was determined based on the pixel distribution in the image (Table 2).

Table 2

Evaluation of Preoperative MRI and Measurement of the Area of the LHB and the Surrounding Effusion Area in Cross-section ^a

	Control Group	Examination Group
Preop MRI, n	16	57
Area effusion LHB, mm²	16	17.8
Area LHB, mm²	55.5	46.6

LHB, long head of the biceps; MRI, magnetic resonance imaging; Preop, preoperative.

Intraoperatively, 31 SLAP lesions and 10 pulley lesions were detected. Furthermore, 46 were intraoperatively assessed by the surgeon (M.K.) as LHB tendinitis due to the degree of the LHB's red coloring. In the examination group, 40 patients were treated with a tenotomy of the LHB, while 31 were treated with a tenodesis.

All demographic, clinical, and intraoperative parameters were examined. A significant association was identified between the presence of a pulley lesion and the group with the least red staining of the LHB (P = .0426, Gr LHB = 0%-10%). Similarly, subacromial impingement likewise had a significant association with the group exhibiting the highest red staining (P = .0321, Gr LHB = 61%-100%).

No significant statistical correlation was found between the intensity and extent of the LHB tendon redness or the surrounding redness in the rotator interval and the corresponding clinical symptoms (such as pain or specific clinical LHB tests) related to LHB pathologies. In addition, preoperative cortisone infiltration did not significantly affect the extent of red coloration of the LHB or the surrounding rotator interval.

Figures 7 and 8 depict the correlation between the red coloration of the LHB and the surrounding rotator cuff interval and the preoperative pain indicated by the patients at the LHB. The data were individually analyzed for both the patient and control groups, represented in accordance with the red coloration of the LHB and the corresponding rotator interval.

Figure 7.

Scoring chart of the pain scale and red coloration of the LHB in the 2 groups. LHB, long head of the biceps.

Figure 8.

Scoring chart of the pain scale and red coloration of the surrounding rotator cuff interval in the 2 groups.

MR Imaging

Preoperative MRI imaging was available for analysis in 73 patients (Table 2, Figures 9 and 10).

Figure 9.

Scoring chart of the threshold area on MRI (mean of effusion area on axial MRI – mean of LHB in the same slice) and red coloration of the LHB in the 2 groups. LHB, long head of the biceps; MRI, magnetic resonance imaging.

Figure 10.

Scoring chart of the threshold area on MRI (mean of effusion area on axial MRI – mean of LHB in the same slice) and red coloration of the rotator cuff interval in the patient group. LHB, long head of the biceps; MRI, magnetic resonance imaging.

Figures 9 and 10 reveal that, on average, the patient group did not exhibit a more extensive effusion area on MRI than the corresponding control group. These figures indicate that the red coloration observed in both the LHB and the corresponding rotator interval does not strongly correlate with the effusion area evident in the preoperative MRI.

Discussion

This study explores whether the red coloring of the LHB and the surrounding rotator cuff interval significantly affects the clinical relevance of assessing LHB tendinitis during arthroscopic visualization. Using an ML program and an image processing program, the study revealed that neither the intensity nor the extent of the red staining of the LHB and surrounding rotator interval correlated with a patient's clinical symptoms. Similarly, no correlation was found between an MRI-detected effusion around the LHB, the red coloration, and the patients’ clinical symptoms.

In some instances of arthroscopic surgery, the red staining of the LHB is used to verify a suspected “inflammation” of the tendon before surgery, particularly when no significant structural lesions (eg, SLAP lesion, tendon tears, or Pulley lesions) are visible. For patients showing ambiguous clinical signs of LHB but experiencing anterior shoulder pain—possibly alongside other concomitant pathologies—surgeons often question whether the LHB should be surgically treated. If one also takes a look at the often low specificity and sensitivity of clinical tests,⁹ this underlines the importance of other parameters for therapy decisions. Visualization of the biceps tendon during arthroscopy is often a decision-making aid for the experienced surgeon. However, this must be questioned based on the available data.

Generally, these are low-risk surgical procedures. However, complications such as increased discomfort (eg, rarely occurring cramps after tenotomy of the LHB), cosmetic losses, or movement restrictions due to scarring could occur. Intriguingly, some patients report the same pain sensation after being treated with a tenotomy or tenodesis.^{7,8,13,13,18,20,29} Persistent postoperative complaints often occur, even with subpectoral tenodesis, where the LHB is entirely excised from the joint and projected onto the LHB. This prompts the question of whether the supposedly inflamed LHB is always the cause of the frequent anterior shoulder pain.

The most prominent visual indicator of a reddened LHB is often referred to as a “lipstick,” which is a broad, fiery red stripe that runs across the LHB. When reviewing the literature, however, it must be noted that although this term is associated with inflammation of the LHB, a precise definition or clinical presentation of symptoms is not provided. In other studies that involve patients with mild clinical anterior shoulder pain and a mildly red coloration of the LHB, the LHB was not treated surgically. Patients displayed satisfactory outcomes through nonoperative treatment for anterior shoulder pain.¹⁵

Artificial intelligence in medicine is becoming increasingly influential in areas of image recognition (MRI, radiograph, and sonography); for example, for early detection of oncological diseases and predicting clinical outcomes after surgical care, or in the education of new surgeons.^{2,4,10,16,17,22,23} The methods of ML and image segmentation are innovative approaches. In this study, a precision of 0.88 was achieved using multiple images and video frames to recognize the LHB. Each detected LHB and the surrounding rotator interval were quantified using different color scales, counting the red pixels. This process facilitated the objectification of the red coloration for both the LHB and the surrounding rotator interval in each image/video frame. Using established ML methods in this study, red staining did not positively correlate with pain originating from the LHB, as evaluated in standard LHB tests. The red staining is due to increased vascular infiltration or expression of the LHB and the surrounding rotator interval.

Conventional MRI diagnostics have a low predictive value for the detection of LHB pathologies.^19,21 Furthermore, this study's evaluation of preoperative MRI imaging suggests that the informative value of this examination is limited when it comes to the question of LHB pathologies. In addition, no positive correlation was found between the red coloration of the LHB, the surrounding rotator interval, and the preoperatively measured effusion area on MRI. The effusion area also demonstrated no positive correlation with the pain reported preoperatively by patients.

Limitations

The fact that the age of the group significantly differs from the control group is a potential limitation. This can be attributed to the types of injuries within the control group, which are often more likely to result from sports or occupational accidents in a patient's history. However, the study was specifically aimed at understanding the presence of red staining, with or without corresponding clinical symptoms. Moreover, no correlation was found between age or sex among the groups with red staining on the LHB. An additional limitation of the study is the lack of follow-up examinations for the patients. Given this, it would be interesting to determine how the clinical outcomes at the LHB/bicipital groove would progress after surgery, depending on the red coloration visualized in an individual patient during the initial surgery.

This study provides an excellent basis for further studies on the topic of LHB tendinitis. It is repeatedly observed that patients have persistent anterior shoulder pain despite LHB tenotomy or tenodesis. It would be interesting to learn how the LHB manifested itself intraoperatively from the redness. This would be interesting to investigate in further prospective studies.

Conclusion

The data show no positive correlation between the redness/intensity of the LHB on arthroscopy and the clinical symptoms within the LHB tests. The assessment of visually detectable “inflammation” of the LHB within arthroscopy as a therapeutic criterion must be questioned. Moreover, no positive correlation was found between the effusion area recorded in the preoperative MRI and the red coloration of the LHB and the surrounding rotator interval, or with the patients’ reported pain.

Footnotes

Final revision submitted February 24, 2025; accepted April 21, 2025.

One or more of the authors has declared the following potential conflict of interest or source of funding: This study was supported by the Open Access Publication Funds of the Ruhr-Universität Bochum. AOSSM checks author disclosures against the Open Payments Database (OPD). AOSSM has not conducted an independent investigation on the OPD and disclaims any liability or responsibility relating thereto.

Ethical approval for this study was obtained from Ruhr Universität Bochum (registration number: 16-5859).

ORCID iD

Maria A. Bernstorff

References

Ahrens

Boileau

The long head of biceps and associated tendinopathy. Bone Jt J. 2007;89-B(8):1001-1009. doi:10.1302/0301-620x.89b8.19278

Chang

Wong

Rasiej

MJ.

Deep learning for the detection of complete anterior cruciate ligament tear. J Digit Imaging. 2019;32(6):980-986. doi:10.1007/s10278-019-00193-4

Chiampas

Ibiebele

AL.

A sports practitioner's perspective on the return to play during the early months of the COVID-19 pandemic: lessons learned and next steps. Sports Med. 2021;51(suppl 1):S89-S96. doi:10.1007/s40279-021-01503-z

Cote

Lubowitz

Brand

Rossi

MJ.

Artificial intelligence, machine learning, and medicine: a little background goes a long way toward understanding. Arthrosc: J Arthrosc Relat Surg. 2021;37(6):1699-1702. doi:10.1016/j.arthro.2021.04.022

Grassbaugh JA

LTC

Bean

MBR

, et al. Refuting the lipstick sign. J Shoulder Elbow Surg. 2017;26(8):1416-1422. doi:10.1016/j.jse.2017.01.009

Habermeyer

Schulterchirurgie. Published online 2017:vi. doi:10.1016/b978-3-437-22342-6.05002-9

Hartland

Islam

Teoh

Rashid

MS.

Clinical effectiveness of tenotomy versus tenodesis for long head of biceps pathology: a systematic review and meta-analysis. BMJ Open. 2022;12(10):e061954. doi:10.1136/bmjopen-2022-061954

Hassan

Patel

Biceps tenodesis versus biceps tenotomy for biceps tendinitis without rotator cuff tears. J Clin Orthop Trauma. 2019;10(2):248-256. doi:10.1016/j.jcot.2018.12.013

Hegedus

Goode

Cook

, et al. Which physical examination tests provide clinicians with the most value when examining the shoulder? Update of a systematic review with meta-analysis of individual tests. Br J Sports Med. 2012;46(14):964. doi:10.1136/bjsports-2012-091066

10.

Hinterwimmer

Lazic

Suren

, et al. Machine learning in knee arthroplasty: specific data are key—a systematic review. Knee Surg, Sports Traumatol, Arthrosc. 2022;30(2):376-388. doi:10.1007/s00167-021-06848-6

11.

Hufeland

Wicke

Verde

Krauspe

Patzer

Biceps tenodesis versus tenotomy in isolated LHB lesions: a prospective randomized clinical trial. Arch Orthop Trauma Surg. 2019;139(7):961-970. doi:10.1007/s00402-019-03136-4

12.

Kikukawa

Segata

Kunitake

Morisawa

Harada

Hirano

MRI of symptomatic shoulders. Orthop Traumatology. 2004;53(2):344-347. doi:10.5035/nishiseisai.53.344

13.

Kooistra

Gurnani

Weening

Deurzen

D van

Bekerom

M van den

. Tenotomy or tenodesis for tendinopathy of the long head of the biceps brachii: an updated systematic review and meta-analysis. Arthrosc, Sports Med, Rehabilitation. 2021;3(4):e1199-e1209. doi:10.1016/j.asmr.2021.02.010

14.

Lee

Jung

Lee

Park

Progression of long head of the biceps brachii tendon abnormality on magnetic resonance imaging after rotator cuff repair. Br J Radiol. 2021;94(1124):20210366. doi:10.1259/bjr.20210366

15.

Light

Plessis

W du

Adsit

, et al. Mild biceps tendonitis may be managed nonoperatively during shoulder arthroscopy. Arthrosc, Sports Med, Rehabilitation. 2023;5(5):100785. doi:10.1016/j.asmr.2023.100785

16.

Lopez

Gazgalis

MDA

Peterson

MDJR

, et al. Machine learning can accurately predict overnight stay, readmission, and 30-day complications following anterior cruciate ligament reconstruction. Arthroscopy. 2023;39(33):777-786.e5. doi:10.1016/j.arthro.2022.06.032

17.

Martin

Ley

Pareek

Groll

Tischer

Seil

Artificial intelligence and machine learning: an introduction for orthopaedic surgeons. Knee Surg, Sports Traumatol, Arthrosc. 2022;30(2):361-364. doi:10.1007/s00167-021-06741-2

18.

Mazzocca

Rios

Romeo

Arciero

RA.

Subpectoral biceps tenodesis with interference screw fixation. Arthrosc: J Arthrosc Relat Surg. 2005;21(7):896.e1-896.e7. doi:10.1016/j.arthro.2005.04.002

19.

McKean

Teh

Imaging of the long head of biceps tendon and rotator interval. Semin Musculoskelet Radiol. 2022;26(05):566-576. doi:10.1055/s-0042-1758850

20.

Moorthy

Tan

AHC

. Should long head of biceps tenodesis or tenotomy be routinely performed in arthroscopic rotator cuff repairs? J Orthop. 2020;21:161-165. doi:10.1016/j.jor.2020.03.033

21.

Morihara

Furukawa

Ito

Kida

Sukenari

Takahashi

Efficacy of biceps-radial-slice magnetic resonance images for the diagnosis of biceps and pulley lesions. J Shoulder Elbow Surg. 2023;32(12):2436-2444. doi:10.1016/j.jse.2023.06.037

22.

Potty

ASR

Maffulli

, et al. Approaching artificial intelligence in orthopaedics: predictive analytics and machine learning to prognosticate arthroscopic rotator cuff surgical outcomes. J Clin Med. 2023;12(6):2369. doi:10.3390/jcm12062369

23.

Poursartip

LeBel

McCracken

, et al. Energy-based metrics for arthroscopic skills assessment. Sensors. 2017;17(8):1808. doi:10.3390/s17081808

24.

Riley

Harrall

Constant

Chard

Cawston

Hazleman

BL.

Tendon degeneration and chronic shoulder pain: changes in the collagen composition of the human rotator cuff tendons in rotator cuff tendinitis. Ann Rheum Dis. 1994;53(6):359. doi:10.1136/ard.53.6.359

25.

Schär

Dellenbach

Pfirrmann

Raniga

Jost

Zumstein

MA.

Many shoulder MRI findings in elite professional throwing athletes resolve after retirement. Clin Orthop Relat Res. 2018;476(3):620-631. doi:10.1007/s11999.0000000000000042

26.

Scheibel

Habermeyer

Aktuelle klinische Untersuchung der Schulter [Current procedures for clinical evaluation of the shoulder]. Orthopade. 2005;34(3):267-283. doi:10.1007/s00132-005-0768-y

27.

Shen

Huang

, et al. Fusing attention mechanism with Mask R-CNN for instance segmentation of grape cluster in the field. Front Plant Sci. 2022;13:934450. doi:10.3389/fpls.2022.934450

28.

Stahnke

Morawietz

Moroder

Scheibel

Synovitis as a concomitant disease in shoulder pathologies. Arch Orthop Trauma Surg. 2019;139(8):1111-1116. doi:10.1007/s00402-019-03152-4

29.

Streit

Shishani

Rodgers

Gobezie

Tendinopathy of the long head of the biceps tendon: histopathologic analysis of the extra-articular biceps tendon and tenosynovium. Open Access J Sports Medicine. 2015;6:63-70. doi:10.2147/oajsm.s76325

30.

Wang

Minnema

Batenburg

Forouzanfar

Multiclass CBCT image segmentation for orthodontics with deep learning. J Dent Res. 2021;100(9):943-949. doi:10.1177/00220345211005338