Current status and prospects of artificial intelligence in breast cancer pathology: convolutional neural networks to prospective Vision Transformers.

Breast cancer is the most prevalent cancer among women, and its diagnosis requires the accurate identification and classification of histological features for effective patient management. Artificial intelligence, particularly through deep learning, represents the next frontier in cancer diagnosis and management. Notably, the use of convolutional neural networks and emerging Vision Transformers (ViT) has been reported to automate pathologists' tasks, including tumor detection and classification, in addition to improving the efficiency of pathology services. Deep learning applications have also been extended to the prediction of protein expression, molecular subtype, mutation status, therapeutic efficacy, and outcome prediction directly from hematoxylin and eosin-stained slides, bypassing the need for immunohistochemistry or genetic testing. This review explores the current status and prospects of deep learning in breast cancer diagnosis with a focus on whole-slide image analysis. Artificial intelligence applications are increasingly applied to many tasks in breast pathology ranging from disease diagnosis to outcome prediction, thus serving as valuable tools for assisting pathologists and supporting breast cancer management.

Does improvement of cognitive functioning by cognitive remediation therapy effect work outcomes in severe mental illness? A secondary analysis of a randomized controlled trial.

AIM: The aim of this study was to clarify whether improvement of cognitive functioning by cognitive remediation therapy can improve work outcome in schizophrenia and other severe mental illnesses when combined with supported employment. METHODS: The subjects of this study were persons with severe mental illness diagnosed with schizophrenia, major depression, or bipolar disorder (ICD-10) and cognitive dysfunction who participated in both cognitive remediation using the Thinking Skills for Work program and a supported employment program in a multisite, randomized controlled study. Logistic and multiple linear regression analyses were performed to clarify the influence of cognitive functioning on vocational outcomes, adjusting for demographic and clinical variables. RESULTS: Improvement of cognitive functioning with cognitive remediation significantly contributed to the total days employed and total earnings of competitive employment in supported employment service during the study period. Any baseline demographic and clinical variables did not significantly contribute to the work-related outcomes. CONCLUSION: A cognitive remediation program transferring learning skills into the real world is useful to increase the quality of working life in supported employment services for persons with severe mental illness and cognitive dysfunction who want to work competitively.

Effects of risperidone and aripiprazole on neurocognitive rehabilitation for schizophrenia.

AIM: Methods to improve neurocognitive impairments are of important research interest. This study sought to examine the synergistic effects of neurocognitive rehabilitation and antipsychotics for schizophrenia. METHODS: Subjects were 43 patients diagnosed with schizophrenia or schizoaffective disorder in a randomized trial of the effects of neurocognitive rehabilitation or a quasi-randomized experimental trial of supported employment with neurocognitive rehabilitation. We compared the effects of risperidone and aripiprazole in neurocognitive rehabilitation for schizophrenia. Subjects were divided into the following groups: (i) the control-risperidone group (CR group) (n = 13); (ii) the rehabilitation-risperidone group (RR group) (n = 9); (iii) the control-aripiprazole group (CA group) (n = 10); and (iv) the rehabilitation-aripiprazole group (RA group) (n = 11). Subjects in the rehabilitation group were engaged in computer-based cognitive exercises (24 sessions) with bridging group (12 sessions) over 12 weeks. Psychiatric symptoms, neurocognitive functioning and social functioning assessments were evaluated at baseline and at 12 weeks. RESULTS: A two-way anova with neurocognitive rehabilitation and antipsychotic medication as factors revealed a significant interaction effect on motor speed. Working memory and motor speed significantly improved in the RA group compared with the CA group. We found no significant improvements between the CR group and the RR group. CONCLUSION: A synergistic effect of neurocognitive rehabilitation and aripiprazole was observed as improvement of motor speed. In patients treated with aripiprazole, neurocognitive rehabilitation appeared to improve working memory and motor speed. Further studies of synergistic effects of neurocognitive rehabilitation and antipsychotic medication are necessary to verify these findings.

Neurocognitive functioning in patients with first-episode schizophrenia 1 year from onset in comparison with patients 5 years from onset.

OBJECTIVE: The course of neurocognitive deficits in schizophrenia has not yet been established. Therefore, we followed patients with first-episode schizophrenia to verify the course of these deficits. METHODS: In Study 1, tests of neurocognitive functioning were administered to patients with first-episode schizophrenia (FE group) every 6 months. Of the 26 patients who completed the baseline assessment, 19 completed a 6-month follow-up, and 13 completed a 1-year follow-up. In Study 2, 19 patients in FE group at 6-months when the neuropsychological measures was less influenced by psychotic symptoms and other patients who experienced schizophrenia 5-years earlier (5-year group) were compared. RESULTS: In Study 1, verbal memory, motor speed, and executive functions significantly improved at the 1-year follow-up. In Study 2, patients in 5-year group performed worse in verbal memory and executive functions than patients in FE at 6-month group, but marginally but significantly better in verbal fluency. CONCLUSIONS: Verbal memory, executive functions, and verbal fluency were significantly different between 5-year group and FE at 6-month group, and may indicate progression of schizophrenia. Executive functions may reflect the state of psychosis. Working memory and processing speed which did not change significantly from onset are needed to verify the course in further research.

Characteristic association of symbol coding test score with occupational function in Japanese patients with schizophrenia.

AIM: Studies showed that cognitive function affects occupational function in patients with schizophrenia. This study aimed to determine the effects of cognitive function on occupational function in Japanese patients with schizophrenia using the Brief Assessment of Cognition in Schizophrenia (BACS). METHODS: Participants were 198 outpatients with schizophrenia or schizoaffective disorder (66 females; mean age 34.5 ± 6.8 years). Occupational function was assessed using the work subscale of the Life Assessment Scale for Mental Ill (LASMI-w). Multiple regression analysis was performed using the BACS as the independent variable and LASMI-w as the dependent variable. Furthermore, we divided the LASMI-w score into three groups, <11, 11-20, and >21, and performed a multinomial logistic regression analysis. RESULTS: Multiple regression analysis revealed that LASMI-w score was negatively associated with BACS composite score (ß = -0.20, p < 0.01). Among the sub-items of the BACS, only the symbol-coding score showed a significant negative association (ß = -0.19, p < 0.05). Multinomial logistic analysis showed that the better the composite and symbol coding scores, the smaller the impairment of the occupational function (composite score: ß = 2.39 between mild and moderate occupational impairments, p < 0.05; symbol coding score: ß = 2.44 between mild and severe impairments, p < 0.05). CONCLUSION: The occupational function of patients with schizophrenia was associated with overall cognitive function (composite score). In particular, the symbol coding score of the BACS was suggested to be related to work ability. These results might be useful in the assessment and training of cognitive rehabilitation aimed at employment support.

Efficacy of cognitive rehabilitation using computer software with individuals living with schizophrenia: A randomized controlled trial in Japan.

OBJECTIVE: Cognitive impairment is common in schizophrenia, and is associated with poor psychosocial functioning. Previous studies had inconsistently shown improvement in cognitive functions with cognitive remediation therapy. This study examined whether cognitive remediation is effective in improving both cognitive and social functions in schizophrenia in outpatient settings that provide learning-based psychiatric rehabilitation. This study is the first randomized controlled trial of cognitive remediation in Japan. METHOD: Study participants were individuals with schizophrenia from 6 outpatient psychiatric medical facilities who were randomly assigned either a cognitive remediation program or treatment as usual. The cognitive remediation intervention includes Cognitive training using computer software (CogPack; Japanese version) administered twice a week and a weekly group over 12 weeks and was based on the Thinking Skills for Work program. Most study participants were attending day treatment services where social skills training, psychoeducation for knowledge about schizophrenia, group activities such as recreation and sport, and other psychosocial treatment were offered. Cognitive and social functioning were assessed using the Brief Assessment of Cognition in Schizophrenia (BACS) and Life Assessment Scale for Mentally Ill (LASMI) at pre- and postintervention. RESULTS: Of the 60 people with schizophrenia enrolled, 29 were allocated to the cognitive remediation group and 31 were allocated to the treatment as usual group. Processing speed, executive function, and the composite score of the BACS showed significantly greater improvement for the cognitive remediation group than the treatment as usual group. In addition, there was significant improvement in interpersonal relationships and work skills on the LASMI for the cognitive remediation group compared with the treatment as usual group. Changes from pretreatment to posttreatment in verbal fluency and interpersonal relationships were significantly correlated, as well as changes in attention and work skills. CONCLUSIONS AND IMPLICATIONS FOR PRACTICE: The present findings showed that providing cognitive remediation on addition to psychiatric rehabilitation contributed to greater improvement in both cognitive and social functioning than psychiatric rehabilitation alone. Cognitive remediation may enhance the efficacy of psychiatric rehabilitation improving social functioning. (PsycINFO Database Record