Implementable assay for monitoring minimum residual disease after radical treatment for colorectal cancer.

Considering the cost and invasiveness of monitoring postoperative minimal residual disease (MRD) of colorectal cancer (CRC) after adjuvant chemoradiotherapy (ACT), we developed a favorable approach based on methylated circulating tumor DNA to detect MRD after radical resection. Analyzing the public database, we identified the methylated promoter regions of the genes FGD5, GPC6, and MSC. Using digital polymerase chain reaction (dPCR), we termed the "amplicon of methylated sites using a specific enzyme" assay as "AMUSE." We examined 180 and 114 pre- and postoperative serial plasma samples from 28 recurrent and 19 recurrence-free pathological stage III CRC patients, respectively. The results showed 22 AMUSE-positive of 28 recurrent patients (sensitivity, 78.6%) and 17 AMUSE-negative of 19 recurrence-free patients (specificity, 89.5%). AMUSE predicted recurrence 208 days before conventional diagnosis using radiological imaging. Regarding ACT evaluation by the reactive response, 19 AMUSE-positive patients during their second or third blood samples showed a significantly poorer prognosis than the other patients (p = 9E-04). The AMUSE assay stratified four groups by the altered patterns of tumor burden postoperatively. Interestingly, only 34.8% of cases tested AMUSE-negative during ACT treatment, indicating eligibility for ACT. The AMUSE assay addresses the clinical need for accurate MRD monitoring with universal applicability, minimal invasiveness, and cost-effectiveness, thereby enabling the timely detection of recurrences. This assay can effectively evaluate the efficacy of ACT in patients with stage III CRC following curative resection. Our study strongly recommends reevaluating the clinical application of ACT using the AMUSE assay.

Tumor suppressive role of the epigenetic master regulator BRD3 in colorectal cancer.

Bromodomain and extraterminal domain (BET) family proteins are epigenetic master regulators of gene expression via recognition of acetylated histones and recruitment of transcription factors and co-activators to chromatin. Hence, BET family proteins have emerged as promising therapeutic targets in cancer. In this study, we examined the functional role of bromodomain containing 3 (BRD3), a BET family protein, in colorectal cancer (CRC). In vitro and vivo analyses using BRD3-knockdown or BRD3-overexpressing CRC cells showed that BRD3 suppressed tumor growth and cell cycle G1/S transition and induced p21 expression. Clinical analysis of CRC datasets from our hospital or The Cancer Genome Atlas revealed that BET family genes, including BRD3, were overexpressed in tumor tissues. In immunohistochemical analyses, BRD3 was observed mainly in the nucleus of CRC cells. According to single-cell RNA sequencing in untreated CRC tissues, BRD3 was highly expressed in malignant epithelial cells, and cell cycle checkpoint-related pathways were enriched in the epithelial cells with high BRD3 expression. Spatial transcriptomic and single-cell RNA sequencing analyses of CRC tissues showed that BRD3 expression was positively associated with high p21 expression. Furthermore, overexpression of BRD3 combined with knockdown of, a driver gene in the BRD family, showed strong inhibition of CRC cells in vitro. In conclusion, we demonstrated a novel tumor suppressive role of BRD3 that inhibits tumor growth by cell cycle inhibition in part via induction of p21 expression. BRD3 activation might be a novel therapeutic approach for CRC.

Pre-existing Interstitial Lung Abnormalities and Immune Checkpoint Inhibitor-Related Pneumonitis in Solid Tumors: A Retrospective Analysis.

BACKGROUND: Immune checkpoint inhibitors (ICIs) have demonstrated efficacy over previous cytotoxic chemotherapies in clinical trials among various tumors. Despite their favorable outcomes, they are associated with a unique set of toxicities termed as immune-related adverse events (irAEs). Among the toxicities, ICI-related pneumonitis has poor outcomes with little understanding of its risk factors. This retrospective study aimed to investigate whether pre-existing interstitial lung abnormality (ILA) is a potential risk factor for ICI-related pneumonitis. MATERIALS AND METHODS: Patients with non-small cell lung cancer, malignant melanoma, renal cell carcinoma, and gastric cancer, who was administered either nivolumab, pembrolizumab, or atezolizumab between September 2014 and January 2019 were retrospectively reviewed. Information on baseline characteristics, computed tomography findings before administration of ICIs, clinical outcomes, and irAEs were collected from their medical records. Pre-existing ILA was categorized based on previous studies. RESULTS: Two-hundred-nine patients with a median age of 68 years were included and 23 (11.0%) developed ICI-related pneumonitis. While smoking history and ICI agents were associated with ICI-related pneumonitis (P = .005 and .044, respectively), the categories of ILA were not associated with ICI-related pneumonitis (P = .428). None of the features of lung abnormalities were also associated with ICI-related pneumonitis. Multivariate logistic analysis indicated that smoking history was the only significant predictor of ICI-related pneumonitis (P = .028). CONCLUSION: This retrospective study did not demonstrate statistically significant association between pre-existing ILA and ICI-related pneumonitis, nor an association between radiologic features of ILA and ICI-related pneumonitis. Smoking history was independently associated with ICI-related pneumonitis. Further research is warranted for further understanding of the risk factors of ICI-related pneumonitis.

Proximity labeling and identification of endogenous client proteins recruited to Y15-based artificial granules tethering a bait protein.

Protein clustering is a ubiquitous event in diverse cellular processes. Self-association of proteins triggers recruitment of downstream proteins to regulate cellular signaling. To investigate the interactions in detail, chemical biology tools to identify proteins recruited to defined assemblies are required. Here, we exploit an identification of proteins recruited in artificial granules (IPRAG) platform that combines intracellular Y15-based supramolecule construction with a proximity labeling method. We validated the IPRAG tool using Nck1 as a target bait protein. We constructed Nck1-tethering granules, labeled the recruited proteins with biotin, and analyzed them by LC-MS/MS. As a result, we successfully identified proteins that directly or indirectly interact with Nck1.

A diagnostic strategy for Parkinsonian syndromes using quantitative indices of DAT SPECT and MIBG scintigraphy: an investigation using the classification and regression tree analysis.

PURPOSE: We aimed to evaluate the diagnostic performances of quantitative indices obtained from dopamine transporter (DAT) single-photon emission computed tomography (SPECT) and 123I-metaiodobenzylguanidine (MIBG) scintigraphy for Parkinsonian syndromes (PS) using the classification and regression tree (CART) analysis. METHODS: We retrospectively enrolled 216 patients with or without PS, including 80 without PS (NPS) and 136 with PS [90 Parkinson's disease (PD), 21 dementia with Lewy bodies (DLB), 16 progressive supranuclear palsy (PSP), and 9 multiple system atrophy (MSA). The striatal binding ratio (SBR), putamen-to-caudate ratio (PCR), and asymmetry index (AI) were calculated using DAT SPECT. The heart-to-mediastinum uptake ratio (H/M) based on the early (H/M [Early]) and delayed (H/M [Delay]) images and cardiac washout rate (WR) were calculated from MIBG scintigraphy. The CART analysis was used to establish a diagnostic decision tree model for differentiating PS based on these quantitative indices. RESULTS: The sensitivity, specificity, positive predictive value, negative predictive value, and accuracy were 87.5, 96.3, 93.3, 92.9, and 93.1 for NPS; 91.1, 78.6, 75.2, 92.5, and 83.8 for PD; 57.1, 95.9, 60.0, 95.4, and 92.1 for DLB; and 50.0, 98.0, 66.7, 96.1, and 94.4 for PSP, respectively. The PCR, WR, H/M (Delay), and SBR indices played important roles in the optimal decision tree model, and their feature importance was 0.61, 0.22, 0.11, and 0.05, respectively. CONCLUSION: The quantitative indices showed high diagnostic performances in differentiating NPS, PD, DLB, and PSP, but not MSA. Our findings provide useful guidance on how to apply these quantitative indices in clinical practice.

Large-Amplitude Thermal Vibration-Coupled Valence Tautomeric Transition Observed in a Conductive One-Dimensional Rhodium-Dioxolene Complex.

The exploration of dynamic molecular crystals is a fascinating theme for materials scientists owing to their fundamental science and potential application to molecular devices. Herein, a one-dimensional (1D) rhodium-dioxolene complex is reported that exhibits drastic changes in properties with the phase transition. X-ray photoelectron spectroscopy (XPS) revealed that the room-temperature (RT) phase is in a mixed-valence state, and therefore, the drastic changes originate from the mixed-valence state appearing in the RT phase. Another notable feature is that the mean square displacements of the rhodium atoms along the 1D chain dramatically increased in the RT phase, indicating a large-amplitude vibration of the Rh-Rh bonds. From these results, a possible mechanism for the appearance of the mixed-valence state in the RT phase was proposed based on the thermal electron transfer from the 1D d-band to the semiquinonato π* orbital coupled with the large-amplitude vibration of the Rh-Rh bonds.

Selection of fluorescent biosensors against galectin-3 from an NBD-modified phage library displaying designed α-helical peptides.

Fluorescent biosensors are indispensable tools for molecular imaging, detection, and drug screening. Conventionally, fluorescent biosensors were constructed by incorporating fluorophores into ligands. Here, to develop ligand-independent biosensors, we demonstrated biosensor selection from a fluorophore-modified peptide phage library. In this library, the peptides were designed to form α-helical structures, and one cysteine, the probe modification site, was located at the center of four randomized residues on the same face of the helix. By conjugation with 4-nitrobenzoxadiazole (NBD), we constructed an NBD-modified phage library. We conducted selection against galectin-3 (Gal-3), a galactose-specific lectin associated with various biological events such as tumor metastasis and insulin resistance. After biopanning, we obtained NBD-modified peptides that selectively bind to Gal-3 from the library. The fluorescence intensity of the hit biosensors increased with the concentration of Gal-3, and this fluorescent response was visually observed.

CT screening for COVID-19 in asymptomatic patients before hospital admission.

INTRODUCTION: In the novel coronavirus disease (COVID-19) pandemic era, it is essential to rule out COVID-19 effectively to prevent transmission in both communities and medical facilities. According to previous reports in high prevalence areas, CT screening may be useful in the diagnosis of COVID-19. However, the value of CT screening in low prevalence areas has scarcely been reported. METHODS: This report examines the diagnostic efficacy of CT screening before admission to a hospital in Tokyo. We conducted a retrospective analysis at Keio University Hospital from April 6, 2020, through May 29, 2020. We set up an outpatient screening clinic on April 6 for COVID-19, administering both PCR with nasopharyngeal swabs and chest CT for all patients scheduled for surgery under general anesthesia. RESULTS: A total of 292 asymptomatic patients were included in this study. There were three PCR-positive patients, and they all had negative CT findings, which revealed that both the sensitivity and positive predictive value of CT (PPV) were 0%. There were nine CT-positive patients; the specificity and the negative predictive value (NPV) were 96.9% and 98.9%, respectively. CONCLUSION: CT screening was not useful in low prevalence areas at this time in Tokyo, even with the inclusion of the most prevalent phase. Given that the utility of CT screening depends on disease prevalence, the criteria for performing CT screening based on the prevalence of COVID-19 should be established.

[A Case of Stenosis at the Junction of the Renal Pelvis and Ureter after Laparoscopic Right Hemicolectomy].

A 50s year old woman was referred to former hospital for abdominal pain and melena. Colonoscopy revealed an ascending colon cancer(cT4aN1bM0, cStage Ⅲb, UICC)and gastrointestinal endoscopy revealed an esophagogastric junction cancer(cT1bN0M0, cStage ⅠA, UICC). Preoperative CT showed mild bilateral hydronephrosis. Laparoscopic right hemicolectomy( Lap-RHC, D3)was performed for ascending colon cancer then, and abdominal CT was taken 2 days before the robot-assisted proximal gastrectomy(RAPG, D1+). Right hydronephrosis was observed. No evidence of obvious ureteral damage was found during Lap-RHC. When retrograde pelvic ureterography was performed and a stenosis was found at the right renal pelvis and ureteral junction. It is considered that the ureter stenosis became prominent due to the postoperative inflammatory change of Lap-RHC. RAPG was performed as scheduled. Two months after discharge, a renal fistula was constructed. Pyeloplasty is scheduled to be performed in the future.

[Results of Surgical Treatment for Gastric Tube Cancer after Esophagectomy].

Recent improvements in the survival of patients after esophagectomy have led to an increase in the occurrence of gastric tube cancers(GTC). We retrospectively examined 7 patients who were surgically treated for GTC among 13 patients who were diagnosed between April 2004 and December 2018. Partial gastrectomy with regional lymph node dissection was performed in 6 patients while total resection of the stomach was performed only in 1 patient. Postoperative complications included 1 anastomotic leakage and 1 subcutaneous abscess. We performed subtotal gastrectomy with preservation of the upper region of the gastric tube in 3 patients. In these patients, blood flow was confirmed from the remnant esophagus to the upper region of the gastric tube using indocyanine green fluorescence imaging. The pathological stage of the treated GTCs were 4 cases of Stage ⅠA, 2 of Stage ⅠB, and 1 of Stage ⅡA. Median follow-up time and postoperative survival time were 32 months and 46.5 months, respectively. Most of our surgically treated cases were early gastric carcinomas that could be radically resected.

Performance of a deep learning-based identification system for esophageal cancer from CT images.

BACKGROUND: Because cancers of hollow organs such as the esophagus are hard to detect even by the expert physician, it is important to establish diagnostic systems to support physicians and increase the accuracy of diagnosis. In recent years, deep learning-based artificial intelligence (AI) technology has been employed for medical image recognition. However, no optimal CT diagnostic system employing deep learning technology has been attempted and established for esophageal cancer so far. PURPOSE: To establish an AI-based diagnostic system for esophageal cancer from CT images. MATERIALS AND METHODS: In this single-center, retrospective cohort study, 457 patients with primary esophageal cancer referred to our division between 2005 and 2018 were enrolled. We fine-tuned VGG16, an image recognition model of deep learning convolutional neural network (CNN), for the detection of esophageal cancer. We evaluated the diagnostic accuracy of the CNN using a test data set including 46 cancerous CT images and 100 non-cancerous images and compared it to that of two radiologists. RESULTS: Pre-treatment esophageal cancer stages of the patients included in the test data set were clinical T1 (12 patients), clinical T2 (9 patients), clinical T3 (20 patients), and clinical T4 (5 patients). The CNN-based system showed a diagnostic accuracy of 84.2%, F value of 0.742, sensitivity of 71.7%, and specificity of 90.0%. CONCLUSIONS: Our AI-based diagnostic system succeeded in detecting esophageal cancer with high accuracy. More training with vast datasets collected from multiples centers would lead to even higher diagnostic accuracy and aid better decision making.

[A Case of Curative Surgery after Infection Control Surgery for Peritonitis Due to Perforation of Rectal Cancer].

A 70s man was admitted to another hospital with a complaint of abdominal pain, and was diagnosed with a gastrointestinal perforation based on the presence of free air in the abdominal cavity on computed tomography. The patient was transferred to our hospital in shock and underwent emergency surgery. Operative findings showed a perforation of the rectosigmoid colon and rectal cancer at the anal side of the perforation site. As his general condition was unstable due to septic shock, only the segments of the colon including the perforation site and rectal cancer were resected for source control. The abdominal wall was kept open, and intraperitoneal contamination was managed with an open management method using negative pressure wound therapy. Systemictreatments for septicshoc k were performed in the intensive care unit with a vasopressor and polymyxin-B hemoperfusion. The general condition became stable with intensive care by postoperative day 3. We performed additional lymph node dissection and one-step rectal sigmoidoscopic anastomosis on postoperative day 4. The pathological results confirmed pT4aN1M0, pStage Ⅲa disease. Although the course was complicated by postoperative pneumonia, the patient was discharged on postoperative day 28. We experienced a case in which curative resection with radical lymph node dissection and one-step anastomosis were performed after infection and source control with open abdomen management.

Value of a Computer-aided Detection System Based on Chest Tomosynthesis Imaging for the Detection of Pulmonary Nodules.

Purpose To assess the value of a computer-aided detection (CAD) system for the detection of pulmonary nodules on chest tomosynthesis images. Materials and Methods Fifty patients with and 50 without pulmonary nodules underwent both chest tomosynthesis and multidetector computed tomography (CT) on the same day. Fifteen observers (five interns and residents, five chest radiologists, and five abdominal radiologists) independently evaluated tomosynthesis images of 100 patients for the presence of pulmonary nodules in a blinded and randomized manner, first without CAD, then with the inclusion of CAD marks. Multidetector CT images served as the reference standard. Free-response receiver operating characteristic analysis was used for the statistical analysis. Results The pooled diagnostic performance of 15 observers was significantly better with CAD than without CAD (figure of merit [FOM], 0.74 vs 0.71, respectively; P = .02). The average true-positive fraction and false-positive rate per all cases with CAD were 0.56 and 0.26, respectively, whereas those without CAD were 0.47 and 0.20, respectively. Subanalysis showed that the diagnostic performance of interns and residents was significantly better with CAD than without CAD (FOM, 0.70 vs 0.62, respectively; P = .001), whereas for chest radiologists and abdominal radiologists, the FOM with CAD values were greater but not significantly: 0.80 versus 0.78 (P = .38) and 0.74 versus 0.73 (P = .65), respectively. Conclusion CAD significantly improved diagnostic performance in the detection of pulmonary nodules on chest tomosynthesis images for interns and residents, but provided minimal benefit for chest radiologists and abdominal radiologists. © RSNA, 2017 Online supplemental material is available for this article.

[A Case of Laparoscopy Assisted Ileocecal Resection for Large Appendiceal Mucinous Adenocarcinoma].

Appendiceal mucinous adenocarcinoma accompanied by cysts ruptures by surgical operation and leakage of mucus into the peritoneal cavity results in deterioration of prognosis.We report a case where the appendix mucinous adenocarcinoma was safely excised by laparoscopically preceding vascular treatment, lymph node dissection and intestinal dissection.The case was a woman in her forty-age suffering from the right lower quadrant and fever; no improvement was observed even when antibiotics were administered.A cystic lesion with a maximum diameter of 75mm was found on the right side of the pelvis with CT, and numerous lymph adenopathy was observed along the iliac artery.Preoperative diagnosis was diagnosed as appendiceal mucinous adenocarcinoma suspected and laparoscopic resection of the cecum was performed with the above procedure without breaking the cyst.Pathological diagnosis was findings of appendicular mucinous adenocarcinoma.She was discharged on the 7th postoperative day after surgery, 6 months after surgery without relapse survival.In order to resect a cystic tumor by laparoscopic surgery, it is considered to be useful to take care to prevent the forceps from touching the tumor, and perform a procedure that precedes vascular dissection and intestinal dissection.

CT imaging before transcatheter aortic valve implantation (TAVI) using variable helical pitch scanning and its diagnostic performance for coronary artery disease.

OBJECTIVES: To evaluate the effectiveness of CT before TAVI using variable helical pitch (VHP) scanning and its diagnostic performance for coronary artery disease (CAD). METHODS: Sixty patients (84.4 ± 4.6 years) scheduled for TAVI underwent CT using VHP scanning with the contrast material (CM) volume calculated as scanning time × weight [kg] × 0.06 mL. Retrospective electrocardiography (ECG)-gated scanning was utilized to examine the thorax, and non-ECG-gated scanning of the abdomen immediately followed. We analyzed CT attenuation values of the coronary arteries, aorta, iliac and femoral arteries. The coronary CT angiography images were evaluated for the presence of stenosis (≥50 %); invasive coronary angiography served as a reference standard. RESULTS: The average attenuations of all of the arteries were greater than 400 HU. We could evaluate the peripheral access vessels and dimensions of the ascending aorta, aortic root, and aortic annulus in all patients. The average volume of CM was 38.7 ± 8.5 mL. On per-patient and vessel analysis, CT showed 91.7 % and 89.5 % sensitivity, and 91.3 % and 97.4 % negative predictive value (NPV). CONCLUSIONS: CT using VHP scanning with an average CM volume of 38.7 mL is useful before TAVI and had a high sensitivity and NPV in excluding obstructive CAD. KEY POINTS: • TAVI-planning CT using variable helical pitch (VHP) scanning is useful. • The average volume of contrast material was 38.7 ± 8.5 mL. • The average attenuations of all the arteries were >400 HU. • This CT had a high sensitivity and NPV for excluding obstructive CAD.

CT Dose Reduction for Visceral Adipose Tissue Measurement: Effects of Model-Based and Adaptive Statistical Iterative Reconstructions and Filtered Back Projection.

OBJECTIVE: The objective of our study was to evaluate the effects of radiation dose reduction and the reconstruction algorithm used--filtered back projection (FBP), adaptive statistical iterative reconstruction (ASIR), or model-based iterative reconstruction (MBIR)--on the measurement of abdominal visceral fat using CT. SUBJECTS AND METHODS: Standard-dose and low-dose abdominal CT examinations were performed simultaneously with automatic exposure control in 59 patients; the noise index for a 5-mm slice thickness was 12 for routine-dose CT and 24 for low-dose CT. The routine-dose CT images were reconstructed using FBP (reference standard), and the low-dose CT images were reconstructed using FBP, ASIR (so-called hybrid iterative reconstruction [IR]), and MBIR (so-called pure IR). In the 236 image series obtained, the visceral fat area was measured. Data were analyzed by the Pearson correlation coefficient test and a Bland-Altman difference analysis. RESULTS: The radiation dose of the low-dose abdominal CT examinations was 73.0% (mean) lower than that of routine-dose CT examinations. Excellent correlations were observed between the visceral fat areas measured on the routine-dose FBP images and those measured on the low-dose FBP, low-dose ASIR, and low-dose MBIR images (r = 0.998, 0.998, and 0.998, respectively; p < 0.001). A Bland-Altman difference analysis revealed excellent agreements, with mean biases of -0.47, -0.41, and 0.18 cm(2) for the visceral fat area between the routine-dose FBP images and the low-dose FBP, low-dose ASIR, and low-dose MBIR images, respectively. CONCLUSION: A 73.0% reduction of the radiation dose would be possible in CT for the measurement of the abdominal visceral fat regardless of which reconstruction algorithm is used (i.e., FBP, hybrid IR, or pure IR).

[Anesthetic Management for Endoscopic Sinus Surgery in a Patient with Transplanted Heart--A Case Report].

A 19-year-old male patient with transplanted heart received endoscopic sinus surgery. He was with X-linked dilated cardiomyopathy, and was one year after the transplantation. Preanesthetic study showed lactate dehydrogenase elevation estimated to have derived from striated muscle. Heart function was normal, and other abnormal findings were not revealed. Total intravenous anesthesia was performed with propofol target controlled infusion and remifentanil. Rocuronium was administered only for oro-tracheal ntubation. After the operation, train-of-four ratio was 95%, and he awoke from anesthesia smoothly. We did not use atropine, neostigmine or sugammadex to reverse neuromuscular blockade. No inotropic agent was administered. He was discharged from the hospital 5 days after the operation without any complications. We used usual anesthetic management but we had to be careful about both denervated heart and myopathy.

Artificial intelligence-enabled prediction of chemotherapy-induced cardiotoxicity from baseline electrocardiograms.

Anthracyclines can cause cancer therapy-related cardiac dysfunction (CTRCD) that adversely affects prognosis. Despite guideline recommendations, only half of the patients undergo surveillance echocardiograms. An AI model detecting reduced left ventricular ejection fraction from 12-lead electrocardiograms (ECG) (AI-EF model) suggests ECG features reflect left ventricular pathophysiology. We hypothesized that AI could predict CTRCD from baseline ECG, leveraging the AI-EF model's insights, and developed the AI-CTRCD model using transfer learning on the AI-EF model. In 1011 anthracycline-treated patients, 8.7% experienced CTRCD. High AI-CTRCD scores indicated elevated CTRCD risk (hazard ratio (HR), 2.66; 95% CI 1.73-4.10; log-rank p < 0.001). This remained consistent after adjusting for risk factors (adjusted HR, 2.57; 95% CI 1.62-4.10; p < 0.001). AI-CTRCD score enhanced prediction beyond known factors (time-dependent AUC for 2 years: 0.78 with AI-CTRCD score vs. 0.74 without; p = 0.005). In conclusion, the AI model robustly stratified CTRCD risk from baseline ECG.

Ensemble detection of hand joint ankylosis and subluxation in radiographic images using deep neural networks.

The modified total Sharp score (mTSS) is often used as an evaluation index for joint destruction caused by rheumatoid arthritis. In this study, special findings (ankylosis, subluxation, and dislocation) are detected to estimate the efficacy of mTSS by using deep neural networks (DNNs). The proposed method detects and classifies finger joint regions using an ensemble mechanism. This integrates multiple DNN detection models, specifically single shot multibox detectors, using different training data for each special finding. For the learning phase, we prepared a total of 260 hand X-ray images, in which proximal interphalangeal (PIP) and metacarpophalangeal (MP) joints were annotated with mTSS by skilled rheumatologists and radiologists. We evaluated our model using five-fold cross-validation. The proposed model produced a higher detection accuracy, recall, precision, specificity, F-value, and intersection over union than individual detection models for both ankylosis and subluxation detection, with a detection rate above 99.8% for the MP and PIP joint regions. Our future research will aim at the development of an automatic diagnosis system that uses the proposed mTSS model to estimate the erosion and joint space narrowing score.