In　this　paper,a　more　optimal　breast　cancer　detection　model　based　on　ResNet　and　random　forest　models　is　developed　based　on　the　combination　of　diagnostic　methods　of　breast　cancer　pathology　slice　images　and　breast　cancer　detection　studies.　The　proposed　model　is　based　on　ResNet　to　classify　breast　MRI　images,　and　random　forest　to　select　some　samples　and　their　features　to　compensate　for　the　overfitting　of　ResNet　in　small　sample　data,　and　random　forest　to　compensate　for　the　overfitting　of　ResNet　in　small　sample　data.The　random　forest　compensates　the　disadvantage　that　ResNet　generates　a　lot　of　redundancy　when　the　sample　features　are　of　high　dimension.After　the　two　models　complement　each　other,the　efficiency　of　image　processing　and　the　accuracy　of　image　classification　of　the　model　are　improved.Finally,a　statistical　analysis　of　the　test　results　of　the　breast　cancer　detection　model　in　this　paper　concluded　that　this　model　is　more　accurate　and　efficient　in　detecting　classified　breast　cancer　than　a　single　machine　learning　model.　　©　2023　IEEE.