KM Research Hub

P1 · PANEL / ROI / AXIS GROUND TRUTH

原 EXE 对齐基准真值复核

所有保存均写入追加式审计事件;旧标注、旧比较和旧提取结果不会被删除或覆盖。

返回质量诊断
冻结记录120
真值完整117
待复核0
无效/退役3
← 上一例 Case 31 / 120 · DB #31 下一例 →
gray_or_same_color pending PMID 41043314

Beyond the first cut: Impact of repeat surgery versus boost on breast induration-A post hoc analysis from the DBCG HYPO & PBI trials.

fig1 · Panel Induration_grade_2-3 · Cumulative incidence of breast induration

Fig. 1 Cumulative incidence of breast induration: Repeat surgery yes/no. The cumulative incidence of grade 2–3 breast induration at 3 and 5 years, estimated at 3.5 and 5.5 years, respectively. RS, repeat surgery. NoRS, no repeat surgery. HR, hazard ratio; Unadj., unadjusted; adj. HR was adjusted for age, smoking status, irradiated volume (V95 %), endocrine therapy, and dose/fractionation.
打开论文记录

坐标框复核

洋红 = 当前 Linux 候选;绿色 = 已保存人工真值。没有绿色框表示仍未形成真值。

Case 31 ROI review overlay
当前候选 {'x0': 118, 'y0': 29, 'x1': 643, 'y1': 376} 人工真值 {'x0': 118, 'x1': 643, 'y0': 29, 'y1': 376}
生产预期曲线2
当前恢复曲线2
算法版本legacy-0.5.0
坐标 OCR完整
查看候选 OCR 与警告(只能作种子,不能自证真值)
{
  "complete": true,
  "engine": "RapidOCR",
  "plot_bottom": 375,
  "plot_left": 118,
  "plot_right": 642,
  "plot_top": 29,
  "warnings": [],
  "x_axis_y": 376,
  "x_confidence": 0.994,
  "x_detected": true,
  "x_max": 6,
  "x_min": 0,
  "x_ticks": [
    {
      "box": [
        [
          110.0,
          386.0
        ],
        [
          126.0,
          386.0
        ],
        [
          126.0,
          406.0
        ],
        [
          110.0,
          406.0
        ]
      ],
      "confidence": 0.9692944884300232,
      "pixel": 118.0,
      "text": "0",
      "value": 0.0
    },
    {
      "box": [
        [
          285.0,
          386.0
        ],
        [
          301.0,
          386.0
        ],
        [
          301.0,
          406.0
        ],
        [
          285.0,
          406.0
        ]
      ],
      "confidence": 0.9996914863586426,
      "pixel": 293.0,
      "text": "2",
      "value": 2.0
    },
    {
      "box": [
        [
          372.0,
          386.0
        ],
        [
          388.0,
          386.0
        ],
        [
          388.0,
          405.0
        ],
        [
          372.0,
          405.0
        ]
      ],
      "confidence": 0.9985429048538208,
      "pixel": 380.0,
      "text": "3",
      "value": 3.0
    },
    {
      "box": [
        [
          460.0,
          386.0
        ],
        [
          474.0,
          386.0
        ],
        [
          474.0,
          404.0
        ],
        [
          460.0,
          404.0
        ]
      ],
      "confidence": 0.9998261332511902,
      "pixel": 467.0,
      "text": "4",
      "value": 4.0
    },
    {
      "box": [
        [
          548.0,
          386.0
        ],
        [
          562.0,
          386.0
        ],
        [
          562.0,
          405.0
        ],
        [
          548.0,
          405.0
        ]
      ],
      "confidence": 0.9997280240058899,
      "pixel": 555.0,
      "text": "5",
      "value": 5.0
    },
    {
      "box": [
        [
          634.0,
          385.0
        ],
        [
          650.0,
          385.0
        ],
        [
          650.0,
          406.0
        ],
        [
          634.0,
          406.0
        ]
      ],
      "confidence": 0.9991958737373352,
      "pixel": 642.0,
      "text": "6",
      "value": 6.0
    }
  ],
  "y_axis_x": 118,
  "y_confidence": 0.941,
  "y_detected": true,
  "y_max": 25,
  "y_min": 0,
  "y_ticks": [
    {
      "box": [
        [
          67.0,
          86.0
        ],
        [
          110.0,
          88.0
        ],
        [
          109.0,
          111.0
        ],
        [
          66.0,
          109.0
        ]
      ],
      "confidence": 0.9997371633847555,
      "pixel": 98.5,
      "text": "20%",
      "value": 20.0
    },
    {
      "box": [
        [
          67.0,
          156.0
        ],
        [
          112.0,
          156.0
        ],
        [
          112.0,
          179.0
        ],
        [
          67.0,
          179.0
        ]
      ],
      "confidence": 0.9996668299039205,
      "pixel": 167.5,
      "text": "15%",
      "value": 15.0
    },
    {
      "box": [
        [
          67.0,
          226.0
        ],
        [
          110.0,
          226.0
        ],
        [
          110.0,
          248.0
        ],
        [
          67.0,
          248.0
        ]
      ],
      "confidence": 0.999664843082428,
      "pixel": 237.0,
      "text": "10%",
      "value": 10.0
    },
    {
      "box": [
        [
          77.0,
          293.0
        ],
        [
          111.0,
          295.0
        ],
        [
          110.0,
          318.0
        ],
        [
          76.0,
          316.0
        ]
      ],
      "confidence": 0.9901153743267059,
      "pixel": 305.5,
      "text": "5%",
      "value": 5.0
    },
    {
      "box": [
        [
          77.0,
          365.0
        ],
        [
          112.0,
          365.0
        ],
        [
          112.0,
          386.0
        ],
        [
          77.0,
          386.0
        ]
      ],
      "confidence": 0.9994171261787415,
      "pixel": 375.5,
      "text": "0%",
      "value": 0.0
    }
  ]
}
查看当前 Linux 输出

追加一条审查结论

选择“有效 KM”时,四边 ROI、四个坐标范围、Panel、终点和曲线数均为必填。

像素 ROI(x1/y1 为排他边界)
真实坐标范围

追加式审计历史

最新事件仅作为当前缓存;以下每一条既往结论都永久保留。

事件时间 / 审查人状态ROI坐标说明
#34p1-visual-axis-audit-v2 · frozen benchmark contact sheets + original images + RapidOCR re-audit 2026-07-28T15:12:18+00:00Codex-assisted visual audit valid_km {'x0': 118, 'x1': 643, 'y0': 29, 'y1': 376} X 0.0–6.0 / Y 0.0–25.0 P1 冻结原图审查;RapidOCR 刻度重审 + 联系表视觉核验;ROI 四边按可见坐标轴框记录。

最近一次正式比较

Suite #3 · 2026-07-28T15:15:12+00:00

未通过

真值完整 117 / 120;通过 0;缺真值 0;无效案例 3。