Investigation of deep learning model for predicting immune checkpoint inhibitor treatment efficacy on contrast-enhanced computed tomography images of hepatocellular carcinoma.

Although the use of immune checkpoint inhibitors (ICIs)-targeted agents for unresectable hepatocellular carcinoma (HCC) is promising, individual response variability exists. Therefore, we developed an artificial intelligence (AI)-based model to predict treatment efficacy using pre-ICIs contrast-enhanced computed tomography (CT) imaging characteristics. We evaluated the efficacy of atezolizumab and bevacizumab in 43 patients at the Nagasaki University Hospital from 2020 to 2022 using the modified Response Evaluation Criteria in Solid Tumors. A total of 197 Progressive Disease (PD), 271 Partial Response (PR), and 342 Stable Disease (SD) contrast CT images of HCC were used for training. We used ResNet-18 as the Convolutional Neural Network (CNN) model and YOLOv5, YOLOv7, YOLOv8 as the You Only Look Once (YOLO) model with precision-recall curves and class activation maps (CAMs) for diagnostic performance evaluation and model interpretation, respectively. The 3D t-distributed Stochastic Neighbor Embedding was used for image feature analysis. The YOLOv7 model demonstrated Precision 53.7%, Recall 100%, F1 score 69.8%, mAP@0.5 99.5% for PD, providing accurate and clinically versatile predictions by identifying decisive points. The ResNet-18 model had Precision 100% and Recall 100% for PD. However, the CAMs sites did not align with the tumors, suggesting the CNN model is not predicting that a given CT slice is PD, PR, or SD, but that it accurately predicts Individual Patient's CT slices. Preparing substantial training data for tumor drug effect prediction models is challenging compared to general tumor diagnosis models; hence, large-scale validation using an efficient YOLO model is warranted.

Probucol Trial for Secondary Prevention of Atherosclerotic Events in Patients with Coronary Heart Disease (PROSPECTIVE).

AIMS: Although intensive statin therapy reduced cardiovascular risks, cardiovascular events have not been completely prevented. Probucol is a potent antioxidant and reduces tendon xanthomas in familial hypercholesterolemia patients despite reduction of high-density lipoprotein (HDL)-cholesterol (HDL-C). We investigated whether probucol can reduce cardiovascular events on top of conventional lipid-lowering therapy in patients with coronary heart disease (CHD). METHODS: PROSPECTIVE is a multicenter, randomized, prospective study that recruited 876 Japanese patients with CHD and dyslipidemia with a low-density lipoprotein (LDL)-cholesterol (LDL-C) level of ≥ 140 mg/dL without medication or those treated with lipid-lowering drugs. Lipid-lowering agents were administered during the study period in the control group (n=438), and probucol 500 mg/day was added to lipid-lowering therapy in the probucol group (n=438). Patients were randomly assigned to two treatment groups by adjusting the LDL-C level and presence of diabetes and hypertension and followed up for more than 3 years. The primary end point was a composite of cerebrovascular and cardiovascular events (cardiovascular disease death including sudden death, nonfatal myocardial infarction, nonfatal stroke, hospitalization for unstable angina, hospitalization for heart failure, or coronary revascularization). The secondary end point was carotid intima-media thickness in a subset of patients. RESULTS: The incidence of the primary end point showed a trend to be lower in the probucol group compared with that in the control group despite reduced HDL-C without serious adverse events. Anti-atherogenic effects of probucol may be attributed to its potent antioxidative function and enhancement of reverse cholesterol transport. CONCLUSION: Since there was no statistical significance between the probucol and control groups despite a marked reduction of HDL-C, further studies on the clinical outcomes of probucol on top of conventional therapy may be necessary in the future (UMIN000003307).

Multicenter phase III trial of regenerative treatment for chronic tympanic membrane perforation.

OBJECTIVE: To evaluate the efficacy and safety of regenerative treatment for tympanic membrane perforation (TMP) using gelatin sponge, basic fibroblast growth factor (bFGF), and fibrin glue. METHODS: This was a multicenter, non-randomized, single-arm study conducted at tertiary referral centers. Twenty patients with chronic TMP (age 23-78 years, 6 males, 14 females) were registered from three institutions. All treated patients were included in the safety analysis population. The edges of the TMP were disrupted mechanically by myringotomy and several pieces of gelatin sponge immersed in bFGF were placed and fixed with fibrin glue to cover the perforation. The TMP was examined 4 ± 1 weeks later. The protocol was repeated up to four times until closure was complete. The main outcome measures were closure or a decrease in size of the TMP, hearing improvement, and air-bone gap evaluated 16 weeks after the final regenerative procedure (FRP). Adverse events (AEs) were monitored throughout the study. RESULTS: Total closure of the TMP at 16 weeks was achieved in 15 out of 20 patients (75.0%, 95% confidence interval [CI]: 50.9%-91.3%) and the mean decrease in size was 92.2% (95%CI: 82.9%-100.0%). The ratio of hearing improvement and the air-bone gap at 16 weeks after FRP were 100% (20/20; 95%CI: 83.2%-100%) and 5.3 ± 4.2 dB (p <0.0001), respectively. Thirteen out of 20 patients (65.0%) experienced at least one AE, but no serious AEs occurred. CONCLUSION: The results indicate that the current regenerative treatment for TMP using gelatin sponge, bFGF, and fibrin glue is safe and effective.

Intractable Hepatic Encephalopathy with a Large Portosystemic Shunt Successfully Treated Using Shunt-preserving Disconnection of the Portal and Systemic Circulation.

Hepatic encephalopathy (HE) is a significant symptom of decompensated liver cirrhosis. Occlusion of portosystemic shunts is used to treat refractory HE. Nevertheless, these treatments often cause adverse events, such as ascites and esophageal varices. We treated a 57-year-old man with refractory HE using shunt-preserving disconnection of the portal and systemic circulation (SPDPS). After SPDPS, there were no obvious complications, and the patient's ammonia level significantly decreased. To date, the patient has not experienced recurrent HE. SPDPS appears to be a safe and effective treatment method for portosystemic encephalopathy.

Regenerative treatment for tympanic membrane perforation using gelatin sponge with basic fibroblast growth factor.

OBJECTIVE: The objective of this study was to evaluate safety and efficacy of regenerative treatment using gelatin sponge with basic fibroblast growth factor (bFGF) in patients with tympanic membrane perforation (TMP). METHODS: The current study was a prospective, multicenter, open-label, single-arm, and exploratory clinical trial to evaluate the safety and efficacy of the TM regeneration procedure (TMRP). Myringotomy was used to mechanically disrupt the edge of the TMP, and a gelatin sponge immersed in bFGF was then placed over the perforation. Fibrin glue was dripped over the sponge as a sealant. TMP closure was examined 4 weeks later and, if insufficient, TMRP was repeated a maximum of three more times. TMP closure and hearing improvement 12 weeks after the final TMRP as well as safety were evaluated. RESULTS: Of the 11 patients with TMP who participated in this study, one who fulfilled the exclusion criteria and did not undergo TMRP and one with cholesteatoma were excluded from the efficacy analysis. TMP closure and hearing improvement 12 weeks after the final TMRP were achieved in eight out of nine patients (88.9%). Mean bone conduction threshold significantly improved 12 weeks after the TMRP compared with baseline (35.7±20.3 vs 29.4±21.0dB, P=0.015). Six out of ten patients receiving TMRP experienced temporary adverse events: appendicitis (serious, severe), otorrhea (mild), otitis media (mild), and sudden hearing loss (mild). However, none were related to the protocol treatment. CONCLUSION: TMP closure and hearing improvement were frequently confirmed following the TMRPs which were safely performed. These favorable outcomes were accompanied with significant improvement of the bone conduction threshold. These promising outcomes would encourage a large-scaled, randomized and pivotal clinical trial in the future. This trial is registered at http://www.umin.ac.jp/ctr/index.htm (identifier: UMIN000006585).